Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    book reviews and related language.

    oai_token-act-pair · gemini-2.0-flash

    diverse topics

    np_token-act-pair-logits · gpt-4o-mini

    books

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.85
    ValueStyle
    -0.83
     author
    -0.82
    oredCriteria
    -0.77
    RegressionTest
    -0.77
    UnusedPrivate
    -0.77
    afficheront
    -0.74
     Author
    -0.74
    RegistryLite
    -0.72
    author
    -0.70
    POSITIVE LOGITS
    SCRIBE
    0.49
     Puritans
    0.48
    ourite
    0.47
    Kjelder
    0.47
    itudinal
    0.47
     Aristotle
    0.46
    MeasureSpec
    0.45
     MutableLiveData
    0.45
    parametric
    0.45
    ῃ
    0.44
    Act Density 2.495%

    No Known Activations